Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2503.23538 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917972148224000 |
|---|---|
| author | Han, Jiyeon Kwon, Dahee Lee, Gayoung Kim, Junho Choi, Jaesik |
| author_facet | Han, Jiyeon Kwon, Dahee Lee, Gayoung Kim, Junho Choi, Jaesik |
| contents | Recent text-to-image generative models, particularly Stable Diffusion and its distilled variants, have achieved impressive fidelity and strong text-image alignment. However, their creative capability remains constrained, as including `creative' in prompts seldom yields the desired results. This paper introduces C3 (Creative Concept Catalyst), a training-free approach designed to enhance creativity in Stable Diffusion-based models. C3 selectively amplifies features during the denoising process to foster more creative outputs. We offer practical guidelines for choosing amplification factors based on two main aspects of creativity. C3 is the first study to enhance creativity in diffusion models without extensive computational costs. We demonstrate its effectiveness across various Stable Diffusion-based models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23538 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Creative Generation on Stable Diffusion-based Models Han, Jiyeon Kwon, Dahee Lee, Gayoung Kim, Junho Choi, Jaesik Computer Vision and Pattern Recognition Recent text-to-image generative models, particularly Stable Diffusion and its distilled variants, have achieved impressive fidelity and strong text-image alignment. However, their creative capability remains constrained, as including `creative' in prompts seldom yields the desired results. This paper introduces C3 (Creative Concept Catalyst), a training-free approach designed to enhance creativity in Stable Diffusion-based models. C3 selectively amplifies features during the denoising process to foster more creative outputs. We offer practical guidelines for choosing amplification factors based on two main aspects of creativity. C3 is the first study to enhance creativity in diffusion models without extensive computational costs. We demonstrate its effectiveness across various Stable Diffusion-based models. |
| title | Enhancing Creative Generation on Stable Diffusion-based Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.23538 |